© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79218
    Prev
    Next
    INDEX
    Explanations

    search query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     വൈദ്യ
    0.50
     மத்தியில்
    0.45
     देर
    0.44
    <unused539>
    0.44
    nienia
    0.44
     verhindern
    0.43
    Ꮠ
    0.42
    ニーズ
    0.42
     ಕಬ್ಬಿಣ
    0.42
    畱
    0.42
    POSITIVE LOGITS
    2
    0.45
     alternative
    0.43
    olik
    0.43
    ვალ
    0.42
    珑
    0.42
     image
    0.41
     informative
    0.40
    大家好
    0.40
    тың
    0.39
    -"
    0.39
    Activations Density 0.002%

    No Known Activations